# Ling 3.0 Flash Benchmark Scores & Performance

> Ling 3.0 Flash by InclusionAI scores 52.2/100 overall, ranking #117 out of 411 AI models.

Canonical page: https://benchlm.ai/models/ling-3-0-flash

Last updated: September 4, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | InclusionAI |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 262K |
| Official model card | [InclusionAI Ling 3.0 Flash model card](https://huggingface.co/inclusionAI/Ling-3.0-flash) |
| Overall Score | 52.2/100 |
| Overall Rank | #117 of 411 |

## Family & Coverage

- Family: Ling 3.0
- Variant: flash
- Benchmarks covered: 38 of 422
- Sibling models: [Ling 3.0 Flash FP8](/models/ling-3-0-flash-fp8), [Ling 3.0 Flash Fin](/models/ling-3-0-flash-fin)
- Related earlier model: [Ling 2.6 Flash](/models/ling-2-6-flash)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 57.0% |
| [AA Tau3 Banking](/benchmarks/aatau3banking) | 28.0% |
| [MCP Atlas](/benchmarks/mcpatlas) | 65.5% |
| [skillsBench](/benchmarks/skillsbench) | 44.8% |
| [BFCL v4](/benchmarks/bfcl-v4) | 73.0% |
| [GDPval-AA](/benchmarks/gdpvalaa) | 1107 |
| [WideResearch](/benchmarks/wideresearch) | 73.6% |
| [BrowseComp](/benchmarks/browsecomp) | 72.2% |
| [DRACO](/benchmarks/draco) | 70.4% |
| [AA Agentic Index](/benchmarks/aaagenticindex) | 29.3% |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 30.3% |
| [Terminal-Bench 2.1 (Vals)](/benchmarks/valsterminalbench21) | 50.2% |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [SWE-bench Pro](/benchmarks/swe-bench-pro) | 56.6% |
| [SWE Multilingual](/benchmarks/swe-bench-multilingual) | 72.4% |
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 57.0% |
| [LiveCodeBench v5](/benchmarks/livecodebench-v5) | 82.8% |
| [SciCode](/benchmarks/scicode) | 41.2% |
| [AA Coding Index](/benchmarks/aacodingindex) | 50.6% |
| [AA-SciCode](/benchmarks/aascicode) | 41.1% |
| [LiveCodeBench (Vals)](/benchmarks/valslivecodebench) | 84.0% |
| [SWE-bench (Vals)](/benchmarks/valsswebench) | 65.2% |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-LCR](/benchmarks/lcr) | 67.0% |
| [CritPt](/benchmarks/critpt) | 1.7% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [GPQA](/benchmarks/gpqa) | 85.0% |
| [GPQA-D](/benchmarks/gpqa-diamond) | 85.0% |
| [HLE](/benchmarks/hle) | 22.7% |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 37.8% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 85.5% |
| [AA-HLE](/benchmarks/aahle) | 23.7% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -17.9% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 18.2% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 44.1% |
| [GPQA Diamond (Vals)](/benchmarks/valsgpqadiamond) | 84.8% |
| [MMLU-Pro (Vals)](/benchmarks/valsmmlupro) | 82.0% |

## Instruction Following Benchmarks

| Benchmark | Score |
|-----------|-------|
| [IFBench](/benchmarks/ifbench) | 74.5% |

## Mathematics Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AIME26](/benchmarks/aime2026) | 93.2% |
| [HMMT Feb 2026](/benchmarks/hmmtfeb2026) | 87.0% |
| [IMOAnswerBench](/benchmarks/imoanswerbench) | 83.7% |

## Other InclusionAI Models

- [Ling 2.6 Flash](/models/ling-2-6-flash) - Score: 43.68
- [Ling 3.0 Flash FP8](/models/ling-3-0-flash-fp8) - Score: not computed
- [Ling 3.0 Flash Fin](/models/ling-3-0-flash-fin) - Score: not computed